Multiple Linear Regression

Pick a response (Y) and check two or more numeric predictors (X). Rows with missing values in any chosen variable are dropped.

Coefficient table — each estimate with its standard error, t-statistic, p-value, and 95% CI, matching summary(lm).

Model F-test tests whether the predictors together explain anything (H₀: all slopes = 0).

R² / adjusted R² — proportion of variation explained; adjusted R² penalizes extra predictors.

Diagnostics — residuals vs fitted (look for random scatter), the residual distribution, and a Cook's-distance flag for high-influence rows.

Predictor relationships — pairwise scatterplots to spot multicollinearity by eye. Expert mode adds the VIF metric.

Multiple Linear RegressionStatLens